Earticle

In transformer cooling systems, oil temperature is controlled through the use of a blower and oil pump. For this paper, set-point algorithms, a reset algorithm and control algorithms of the cooling system were developed by neural networks and fuzzy logics. The oil inlet temperature was set by a 2× 2× 1 neural network, and the oil temperature difference was set by a 2× 3× 1 neural network. Inputs used for these neural networks were the transformer operating ratio and the air inlet temperature. The inlet set temperature was reset by a fuzzy logic based on the transformer operating ratio and the oil outlet temperature. A blower was used to control the inlet oil temperature while the oil pump was used to control the oil temperature difference by fuzzy logics. In order to analysis the performance of these algorithms, the initial start-up test and the step change test were performed by using the dynamic model of a transformer cooling system. Test results showed that algorithms developed for this study were effective in controlling the oil temperature of a transformer cooling system.

In order to improve the efficiency of the main transformer in a tilting train, the optimal operation of a cooling system is necessary. For the development of the optimal control algorithm of a cooling system, the mathematical model of a main transformer cooling system was developed. This includes the dynamic model of a main transformer, an oil pump, an oil cooler and a blower. The system algorithm of a cooling system, which consists of the temperature setpoint algorithm and the temperature control algorithm, was developed. Optimal oil temperatures of the inlet and the outlet of the main transformer were obtained by considering the total electric power consumption of the system. The oil inlet temperature was controlled by the blower and the oil outlet temperature was controlled by the oil pump. A simulation program was developed by using the mathematical model and the system algorithm. Simulation results showed that the system algorithm developed from this study may be effectively used to control the main transformer cooling system in a tilting train.

In order to protect the environment from the refrigerant pollution, the $CO_2$ may be regarded as one of the most attractive alternative refrigerants for an automotive air-conditioning system. Control methods for a $CO_2$ system should be different because of $CO_2$'s unique properties as a refrigerant. Especially, the high-side pressure of a $CO_2$ system should be controlled for the effective operation of the system. In this study, the high-side pressure setpoint algorithm was developed by using a neural network and a Lagrange interpolation method. These methods were compared. Simulation results showed that a Lagrange interpolation method was more effective than a neural network in the respect of its easiness of programming and shorter execution time.